INDEX

Explanations

Words related to specific organizations and initiatives

oai_token-act-pair · gpt-3.5-turbo

references to meetings or gatherings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 constitu

-0.73

tom

-0.70

 compens

-0.69

 determining

-0.68

bably

-0.67

 lengths

-0.66

quo

-0.65

 diver

-0.65

 deduction

-0.65

 conflicting

-0.64

POSITIVE LOGITS

 Yourself

1.30

 Your

1.29

 Them

1.14

Your

1.14

Me

1.02

Me

0.99

away

0.98

 Away

0.96

your

0.96

Safe

0.96

Activations Density 0.241%

Words related to specific organizations and initiatives

references to meetings or gatherings

No Comments

No Known Activations